Table 1. Model’s F1-measure and running time.

The results with 13-mers and weighting are shown. The maximum number of 13-mers selected for the regression model was 1000. In cases where sequencing reads were used as the input, a minimum frequency of 5 for a 13-mer was required to reduce the influence of sequencing errors.

Dataset	F1-measure	Number of isolates		Time for the model building (per model)	Time for the phenotype prediction (per phenotype)
		Training	Testing
Pseudomonas aeruginosa (contigs)	0.88	150	50	3h 36m	0.81s
Pseudomonas aeruginosa (reads)	0.88	150	50	19h 56m	58.0s
Klebsiella pneumoniae (contigs)	0.88	125	42	3h 38m	0.7s
Klebsiella pneumoniae (reads)	0.88	125	42	10h 3m	28.0s
Clostridium difficile (contigs)	0.97	345	115	4h 50m	0.61s
Pseudomonas aeruginosa (contigs)	0.88	150	50	3h 36m	0.81s